US20220345899A1 - Propagation characteristic estimation device, propagation characteristic estimation method, and propagation characteristic estimation program - Google Patents
Propagation characteristic estimation device, propagation characteristic estimation method, and propagation characteristic estimation program Download PDFInfo
- Publication number
- US20220345899A1 US20220345899A1 US17/765,114 US201917765114A US2022345899A1 US 20220345899 A1 US20220345899 A1 US 20220345899A1 US 201917765114 A US201917765114 A US 201917765114A US 2022345899 A1 US2022345899 A1 US 2022345899A1
- Authority
- US
- United States
- Prior art keywords
- distance
- transmitting station
- propagation characteristic
- receiving station
- station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims description 22
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 23
- 238000010801 machine learning Methods 0.000 claims abstract description 17
- 239000000284 extract Substances 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 238000004891 communication Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 10
- 238000013528 artificial neural network Methods 0.000 description 2
- NRNCYVBFPDDJNE-UHFFFAOYSA-N pemoline Chemical compound O1C(N)=NC(=O)C1C1=CC=CC=C1 NRNCYVBFPDDJNE-UHFFFAOYSA-N 0.000 description 2
- 101000582320 Homo sapiens Neurogenic differentiation factor 6 Proteins 0.000 description 1
- 102100030589 Neurogenic differentiation factor 6 Human genes 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
- H04B17/3913—Predictive models, e.g. based on neural network models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/20—Monitoring; Testing of receivers
- H04B17/27—Monitoring; Testing of receivers for locating or positioning the transmitter
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
Definitions
- the present invention relates to a propagation characteristic estimation device, a propagation characteristic estimation method, and a propagation characteristic estimation program.
- a site-specific estimation method is a method of estimating location-specific propagation loss.
- a site-general estimation method is a method of estimating a general propagation characteristic trend that is not location-specific.
- the propagation loss of radio waves is estimated by mainly using land use distribution and topographical information issued by the Geospatial Information Authority of Japan or the like, and giving consideration to the influence of surrounding buildings (see PTL 1 and 2 and NPL 1 and 2).
- NPL 1 N. Kuno, Y. Takatori, “Preddction Method by Deep-Learning for Path Loss Characteristics in an Open-Square Environment,” ISAP 2018, pp. 1-2, October 2018.
- NPL 2 N. Kuno, W. Yamada, M. Sasaki, Y. Takatori, “Convolutional Neural Network for Prediction Method of Path Loss Characteristics considering Diffraction. and Reflection in an Open-Square Environment,” 2019 AP-RASC, pp. 1-3, March 2019.
- An object of the present invention is to provide a propagation characteristic estimation device, a propagation characteristic estimation method, and a propagation characteristic estimation program that are capable of reducing the storage capacity and reading time required for data that is needed to estimate the propagation characteristics of radio waves.
- a propagation characteristic estimation device for estimating a propagation characteristic of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristic estimation device including: an extraction unit configured to, based on input information from an external source, extract position information regarding the transmitting station and the receiving station and a frequency of radio waves transmitted by the transmitting station; a calculation unit configured to calculate a three-dimensional distance between the transmitting station and the receiving station and a free space loss of radio waves based on the position information and the frequency; a processing unit configured to perform processing for, with use of a two-dimensional image of a region that includes the transmitting station and the receiving station, extracting an edge of a structure that reflects radio waves in the two-dimensional image; a generation unit configured to generate input data for use in machine learning, based on the position information, the three-dimensional distance, the free space loss, and the edge; and a learning unit configured to perform machine learning to estimate a propagation characteristic of radio waves between the transmitting
- a propagation characteristic estimation method is a propagation characteristic estimation method for estimating a propagation characteristic of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristic estimation method including: an extraction step of, based on input information from an external source, extracting position information regarding the transmitting station and the receiving station and a frequency of radio waves transmitted by the transmitting station; a calculation step of calculating a three-dimensional distance between the transmitting station and the receiving station and a free space loss of radio waves based on the position information and the frequency; a processing step of performing processing for, with use of a two-dimensional image of a region that includes the transmitting station and the receiving station, extracting an edge of a structure that reflects radio waves in the two-dimensional image; a generation step of generating input data for use in machine learning, based on the position information, the three-dimensional distance, the free space loss, and the edge; and a learning step of performing machine learning to estimate a propagation characteristic of radio waves between the transmit
- FIG. 1 is a diagram showing an overview of a propagation characteristic estimation method according to an embodiment.
- FIG. 2 is a functional block diagram showing functions of a propagation characteristic estimation device according to an embodiment.
- FIG. 3 is a diagram schematically showing processing in which a processing unit extracts edges of a structure in a two-dimensional image.
- FIG. 4 is a diagram illustrating a multi-layer perceptron used by a learning unit.
- FIG. 5 is a flowchart showing an example of operations when the propagation characteristic estimation device performs machine learning.
- FIG. 6 is a flowchart showing a specific example of operations of an input data generation unit.
- FIG. 7 is a diagram showing an example of the hardware configuration of the propagation characteristic estimation device according to an embodiment.
- FIG. 1 is a diagram showing an overview of the propagation characteristic estimation method according to an embodiment.
- the edges of buildings are extracted from a two-dimensional image that shows buildings, the ground surface state, and the like (e.g., a satellite photograph), and building information constituted by the edges is acquired. Then, the position of a fixed station (transmitting station) is set in the two-dimensional image, and the propagation characteristics at a mobile station (receiving station) are estimated.
- a neural network (see FIG. 4 ) capable of nonlinear regression is used for this estimation.
- FIG. 2 is a functional block diagram showing functions of a propagation characteristic estimation device 1 according to one embodiment.
- the propagation characteristic estimation device 1 acquires a two-dimensional image such as a satellite photograph from an image storage unit 2 that stores two-dimensional images that show buildings, the ground surface state, and the like (e.g., satellite photographs), and estimates the propagation characteristics of radio waves inside an area included in the two-dimensional image.
- the image storage unit 2 may be provided in the propagation characteristic estimation device 1 .
- the propagation characteristic estimation device 1 includes an input unit 10 , an input data generation unit 12 , a learning unit 14 , and a model storage unit 16 .
- the input unit 10 includes the functionality of an input device that, in accordance with a user operation, inputs, to the input data generation unit 12 , position information that indicates the positions of a transmitting station and a receiving station for which radio wave propagation characteristics are to be estimated, and information that includes the frequency f of radio waves transmitted by the transmitting station, for example.
- the input data generation unit 12 includes an extraction unit 120 , a calculation unit 122 , an acquisition unit 124 , a processing unit 126 , and a generation unit 128 .
- the extraction unit 120 extracts information such as the position information for the transmitting station and the receiving station and the radio wave frequency f from the information that was received from the input unit 10 , and outputs the extracted information to the calculation unit 122 .
- the calculation unit 122 uses the information that was received from the extraction unit 120 to calculate the three-dimensional distance (slope distance (d 3D ) between the transmitting station and the receiving station and a free space loss L FS of radio waves, and outputs the calculation results and the information that was received from the extraction unit 120 to the acquisition unit 124 and the Generation unit 128 .
- the calculation unit 122 calculates the slope distance d 3D using Expression 1 below.
- d 3D ⁇ square root over (( x Tx ⁇ x Rx ) 2 +( y Tx ⁇ y Rx ) 2 +( z Tx ⁇ z Rx ) 2 ) ⁇ (1)
- the calculation unit 122 calculates the free space loss L FS using Expression 2 below.
- the free space loss L FS is used as a reference for propagation loss L that is learned by the later-described learning unit 14 .
- the acquisition unit 124 acquires a two-dimensional image such as a satellite photograph from the image storage unit 2 , and outputs the acquired two-dimensional image and information such as the calculation results received from the calculation unit 122 to the processing unit 126 .
- the acquisition unit 124 acquires a two-dimensional image of a predetermined area (estimation range) that includes a transmitting station and a receiving station.
- the processing unit 126 uses the two-dimensional image received from the acquisition unit 124 to perform processing for extracting edges of a structure (e.g., a building) that reflects radio waves in the two-dimensional image, and outputs information (e.g., an edge image) that includes the extracted edges to the generation unit 128 .
- a structure e.g., a building
- information e.g., an edge image
- FIG. 3 is a diagram schematically showing processing in which the processing unit 126 extracts edges of a structure in a two-dimensional image. As shown in FIG. 3 , the processing unit 126 performs processing for creating an edge image obtained by extracting only the edges of buildings that reflects radio waves from a satellite photograph (satellite image) of buildings, cars, people, and the like.
- a satellite photograph satellite photograph
- processing unit 126 removes the edges of the structure that corresponds to the transmitting station, and extracts the edges of other structures.
- the processing for removing the edges of the structure that corresponds to the transmitting station may be performed by the generation unit 128 .
- the generation unit 128 has a judgment unit 130 and a determination unit 132 , and is configured to generate input data (input parameters) used for machine learning performed by the learning unit 14 , based on the information received from the calculation unit 122 and the processing unit 126 , and output the input data to the learning unit 14 .
- the information input to the generation unit 128 from the calculation unit 122 and the processing unit 126 includes the position information for the transmitting station and the receiving station, the three-dimensional distance (slope distance d 3D ), the free space loss L FS , and edges (an edge image).
- the judgment unit 130 judges whether or not a line segment that connects the transmitting station and the receiving station intersects an edge, and outputs the judgment result to the determination unit 132 .
- the judgment unit 130 sets the result of the judgment regarding whether or not the line segment intersects an edge as a line-of-sight judgment F LOS . For example, if the judgment unit 130 has judged that the line segment intersects an edge, the line-of-sight judgment F LOS is affirmative. Also, if the judgment unit 130 has judged that the line segment does not intersect an edge, the line-of-sight judgment F LOS is negative.
- the determination unit 132 sets a first distance (d nTx ) to the distance from the transmitting station to the nearest structure edge, and sets a second distance (d nRx ) to the distance from the receiving station to the nearest structure edge. Also, if the judgment unit 130 has judged that the line-of-sight judgment F LOS is negative, the determination unit 132 sets the first distance (d nTx ) and the second distance (d nRx ) to the two-dimensional distance (slope distance d 2D ) between the transmitting station and the receiving station.
- the determination unit 132 then makes a determination that the first distance (d nTx ) and the second distance (d nRx ) that were set are to be included in the input data that is to be used in the machine learning performed by the learning unit 14 .
- the input data used in the machine learning performed by the learning unit 14 includes, for example, the three-dimensional distance (slope distance d3D), the frequency f, the free space loss L FS , the judgment result regarding the line-of-sight judgment F LOS , the first distance (d nTx ), and the second distance (d nRx ).
- the learning unit 14 uses a neural network for example, the learning unit 14 performs machine learning with use of the above-described input data received from the generation unit 128 and the propagation loss L as learning parameters, and stores the learned model in the model storage unit 16 .
- FIG. 4 is a diagram illustrating a multi-layer perceptron used by the learning unit 14 .
- ⁇ represents a weight matrix
- b represents a constant term array.
- the learning unit 14 uses the three-dimensional distance (slope distance d 3D ), the frequency f, the free space loss L FS , the judgment result regarding the line-of-sight judgment F LOS , the first distance (d nTx ), the second distance (d nRx ), and the like as input parameters, the learning unit 14 performs learning to adjust the weights of the layers.
- the propagation characteristic estimation device 1 estimates the propagation characteristics of radio waves between the transmitting station and the receiving station with use of the model stored in the model storage unit 16 .
- FIG. 5 is a flowchart showing an example of operations in the case where the propagation characteristic estimation device 1 performs machine learning.
- the calculation unit 122 calculates the slope distance d 3D using the positions of the transmitting station and the receiving station (transmitting and receiving station positions) (S 100 ). Also, the calculation unit 122 calculates the free space loss L FS (S 102 ).
- the acquisition unit 124 imports a satellite photograph of the estimation range from the image storage unit 2 (S 104 ), and then the processing unit 126 extracts the edges of structures such as buildings included in the satellite photograph (S 106 ).
- the judgment unit 130 calculates the line-of-sight judgment F LOS between the transmitting and receiving stations (S 108 ), and the determination unit 132 performs calculation to determine the distance information (the first distance (d nTx ) and the second distance (d nRx )) between a building and the transmitting and receiving stations (S 110 ).
- the learning unit 14 performs learning using the free space loss L FS , the judgment result regarding the line-of-sight judgment F LOS , the distance information on the distances to the building, and the like (S 112 ).
- FIG. 6 is a flowchart showing a specific example of operations of the input data generation unit 12 .
- the calculation unit 122 calculates the slope distance d 3D using the transmitting and receiving station positions (S 200 ), and sets the slope distance in the propagation characteristic estimation device 1 to d 3D (S 202 ).
- the calculation unit 122 calculates the free space loss L FS using above Expression 2 (S 204 ).
- the processing unit 126 creates an edge image from the two-dimensional image imported by the acquisition unit 124 , and removes the transmitting station building from the created edge image (S 206 ).
- the judgment unit 130 makes the judgment of whether or riot the line segment between the transmitting and receiving stations intersects an edge (S 208 ), and sets the result of the intersection judgment as the line-of-sight judgment F LOS (S 210 ). Then, if the judgment unit 130 has judged that the line-of-sight judgment F LOS is affirmative (S 212 : Yes), the generation unit 128 moves to the processing of S 214 , whereas if the judgment unit 130 has judged that the line-of-sight judgment F LOS is negative (S 212 : No), the generation unit 128 moves to the processing of S 222 .
- the determination unit 132 calculates the distance from the transmitting station to the nearest building (S 214 ) and sets that distance as the first distance (d nTx ) (S 216 ). Also, the determination unit 132 calculates the distance from the receiving station to the nearest building (S 218 ), and sets that distance as the second distance (d nRx ) (S 220 ).
- the determination unit 132 calculates the distance between the transmitting and receiving stations (slope distance d 2D ), and sets that distance as the first distance (d nTx ) and the second distance (d nRx ) (S 224 ).
- the propagation characteristic estimation device 1 uses a two-dimensional image of a region that includes a transmitting station and a receiving station, extracts edges of structures in a two-dimensional image and generates input data that is to be used for machine learning, thus making it possible to reduce the storage capacity and reading time required for data that is needed to estimate the propagation characteristics of radio waves.
- the propagation characteristic estimation device 1 may be constituted by hardware, or may be constituted as a program executed by a processor such as a CPU.
- the propagation characteristic estimation device 1 can be realized using a computer and a program, and the program can be recorded on a storage medium or provided through a network.
- FIG. 7 is a diagram showing an example of the hardware configuration of the propagation characteristic estimation device 1 according to the embodiment.
- an input unit 40 an output unit 41 , a communication unit 42 , a CPU 43 , a memory 44 , and an HDD 45 are connected via a bus 46 , for example, and function as a computer.
- the propagation characteristic estimation device 1 is capable of inputting data to the storage medium 47 and receiving data therefrom.
- the input unit 40 is a keyboard, a mouse, or the like, and corresponds to the above-mentioned input unit 10 .
- the output unit 41 is a display device such as a display.
- the communication unit 42 is a wired and wireless network interface, for example.
- the CPU 43 controls the units that constitute the propagation characteristic estimation device 1 , and performs the above-described calculation and the like.
- the memory 44 and the HDD 45 constitute a storage unit for storing data.
- the memory 44 stores the data used in the above-described calculation.
- the storage medium 47 is capable of storing a propagation characteristic estimation program or the like that executes the functions of the propagation characteristic estimation device 1 . Note that the architecture that constitutes the propagation characteristic estimation device 1 is not limited to the example shown in. FIG. 7
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
Provided are: an extraction unit that, based on input information from an external source, extracts position information regarding a transmitting station and a receiving station and the frequency of radio waves transmitted by the transmitting station; a calculation unit that calculates the three-dimensional distance between the transmitting station and the receiving station and the free space loss of radio waves based on the position information and the frequency; a processing unit that performs processing for, with use of a two-dimensional image of a region that includes the transmitting station and the receiving station, extracting the edges of structures that reflect radio waves in the two-dimensional image; a generation unit that generates input data for use in machine learning, based on the position information, the three-dimensional distance, the free space loss, and the edge; and a learning unit that performs machine learning to estimate the propagation characteristics of radio waves between the transmitting station and the receiving station with use of the input data generated by the generation unit.
Description
- The present invention relates to a propagation characteristic estimation device, a propagation characteristic estimation method, and a propagation characteristic estimation program.
- In wireless communication systems, methods for estimating the propagation loss of radio waves transmitted from a transmitting station to a receiving station are roughly classified into two types, namely site-specific methods and site-general methods. A site-specific estimation method is a method of estimating location-specific propagation loss. On the other hand, a site-general estimation method is a method of estimating a general propagation characteristic trend that is not location-specific.
- For example, in a site-specific estimation method, the propagation loss of radio waves is estimated by mainly using land use distribution and topographical information issued by the Geospatial Information Authority of Japan or the like, and giving consideration to the influence of surrounding buildings (see
PTL 1 and 2 andNPL 1 and 2). - [PTL 1] JP 2014-158110A
- [PTL 2] JP 2019-122008A
- [NPL 1] N. Kuno, Y. Takatori, “Preddction Method by Deep-Learning for Path Loss Characteristics in an Open-Square Environment,” ISAP 2018, pp. 1-2, October 2018.
- [NPL 2] N. Kuno, W. Yamada, M. Sasaki, Y. Takatori, “Convolutional Neural Network for Prediction Method of Path Loss Characteristics considering Diffraction. and Reflection in an Open-Square Environment,” 2019 AP-RASC, pp. 1-3, March 2019.
- However, if the area that includes the transmitting station and the receiving station is large, the amount of surrounding building information that needs to be read in order to estimate the propagation loss of radio waves becomes very large, thus creating the problem of increases in the amount of memory used for reading building information and the amount of time required for reading.
- An object of the present invention is to provide a propagation characteristic estimation device, a propagation characteristic estimation method, and a propagation characteristic estimation program that are capable of reducing the storage capacity and reading time required for data that is needed to estimate the propagation characteristics of radio waves.
- A propagation characteristic estimation device according to an aspect of the present invention is a propagation characteristic estimation device for estimating a propagation characteristic of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristic estimation device including: an extraction unit configured to, based on input information from an external source, extract position information regarding the transmitting station and the receiving station and a frequency of radio waves transmitted by the transmitting station; a calculation unit configured to calculate a three-dimensional distance between the transmitting station and the receiving station and a free space loss of radio waves based on the position information and the frequency; a processing unit configured to perform processing for, with use of a two-dimensional image of a region that includes the transmitting station and the receiving station, extracting an edge of a structure that reflects radio waves in the two-dimensional image; a generation unit configured to generate input data for use in machine learning, based on the position information, the three-dimensional distance, the free space loss, and the edge; and a learning unit configured to perform machine learning to estimate a propagation characteristic of radio waves between the transmitting station and the receiving station with use of the input data generated by the generation unit.
- Also, a propagation characteristic estimation method according to an aspect of the present invention is a propagation characteristic estimation method for estimating a propagation characteristic of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristic estimation method including: an extraction step of, based on input information from an external source, extracting position information regarding the transmitting station and the receiving station and a frequency of radio waves transmitted by the transmitting station; a calculation step of calculating a three-dimensional distance between the transmitting station and the receiving station and a free space loss of radio waves based on the position information and the frequency; a processing step of performing processing for, with use of a two-dimensional image of a region that includes the transmitting station and the receiving station, extracting an edge of a structure that reflects radio waves in the two-dimensional image; a generation step of generating input data for use in machine learning, based on the position information, the three-dimensional distance, the free space loss, and the edge; and a learning step of performing machine learning to estimate a propagation characteristic of radio waves between the transmitting station and the receiving station with use of the input data that was generated.
-
FIG. 1 is a diagram showing an overview of a propagation characteristic estimation method according to an embodiment. -
FIG. 2 is a functional block diagram showing functions of a propagation characteristic estimation device according to an embodiment. -
FIG. 3 is a diagram schematically showing processing in which a processing unit extracts edges of a structure in a two-dimensional image. -
FIG. 4 is a diagram illustrating a multi-layer perceptron used by a learning unit. -
FIG. 5 is a flowchart showing an example of operations when the propagation characteristic estimation device performs machine learning. -
FIG. 6 is a flowchart showing a specific example of operations of an input data generation unit. -
FIG. 7 is a diagram showing an example of the hardware configuration of the propagation characteristic estimation device according to an embodiment. - Embodiments of a propagation characteristic estimation device and a propagation characteristic estimation method will be described below with reference to the drawings.
FIG. 1 is a diagram showing an overview of the propagation characteristic estimation method according to an embodiment. - In the propagation characteristic estimation method according to one embodiment, the edges of buildings are extracted from a two-dimensional image that shows buildings, the ground surface state, and the like (e.g., a satellite photograph), and building information constituted by the edges is acquired. Then, the position of a fixed station (transmitting station) is set in the two-dimensional image, and the propagation characteristics at a mobile station (receiving station) are estimated. A neural network (see
FIG. 4 ) capable of nonlinear regression is used for this estimation. -
FIG. 2 is a functional block diagram showing functions of a propagationcharacteristic estimation device 1 according to one embodiment. The propagationcharacteristic estimation device 1 acquires a two-dimensional image such as a satellite photograph from an image storage unit 2 that stores two-dimensional images that show buildings, the ground surface state, and the like (e.g., satellite photographs), and estimates the propagation characteristics of radio waves inside an area included in the two-dimensional image. The image storage unit 2 may be provided in the propagationcharacteristic estimation device 1. - As shown in
FIG. 2 , the propagationcharacteristic estimation device 1 includes an input unit 10, an input data generation unit 12, alearning unit 14, and amodel storage unit 16. The input unit 10 includes the functionality of an input device that, in accordance with a user operation, inputs, to the input data generation unit 12, position information that indicates the positions of a transmitting station and a receiving station for which radio wave propagation characteristics are to be estimated, and information that includes the frequency f of radio waves transmitted by the transmitting station, for example. - The input data generation unit 12 includes an
extraction unit 120, acalculation unit 122, an acquisition unit 124, a processing unit 126, and a generation unit 128. - The
extraction unit 120 extracts information such as the position information for the transmitting station and the receiving station and the radio wave frequency f from the information that was received from the input unit 10, and outputs the extracted information to thecalculation unit 122. - Using the information that was received from the
extraction unit 120, thecalculation unit 122 calculates the three-dimensional distance (slope distance (d3D) between the transmitting station and the receiving station and a free space loss LFS of radio waves, and outputs the calculation results and the information that was received from theextraction unit 120 to the acquisition unit 124 and the Generation unit 128. - For example, the
calculation unit 122 calculates the slope distance d3D using Expression 1 below. Here, the position of the transmitting station is PTx=(xTx, yTx,zTx), and the position of the receiving station is PRx=(xRx, yRx,zRx). -
[Math 1] -
d 3D=√{square root over ((x Tx −x Rx)2+(y Tx −y Rx)2+(z Tx −z Rx)2)} (1) - Also, the
calculation unit 122 calculates the free space loss LFS using Expression 2 below. The free space loss LFS is used as a reference for propagation loss L that is learned by the later-describedlearning unit 14. -
[Math 2] -
free space loss L FS [db]=32.4+20 log10d3D [km]+20 log10 f [GHz] (2) - The acquisition unit 124 acquires a two-dimensional image such as a satellite photograph from the image storage unit 2, and outputs the acquired two-dimensional image and information such as the calculation results received from the
calculation unit 122 to the processing unit 126. For example, the acquisition unit 124 acquires a two-dimensional image of a predetermined area (estimation range) that includes a transmitting station and a receiving station. - Using the two-dimensional image received from the acquisition unit 124, the processing unit 126 performs processing for extracting edges of a structure (e.g., a building) that reflects radio waves in the two-dimensional image, and outputs information (e.g., an edge image) that includes the extracted edges to the generation unit 128.
-
FIG. 3 is a diagram schematically showing processing in which the processing unit 126 extracts edges of a structure in a two-dimensional image. As shown inFIG. 3 , the processing unit 126 performs processing for creating an edge image obtained by extracting only the edges of buildings that reflects radio waves from a satellite photograph (satellite image) of buildings, cars, people, and the like. - Note that the processing unit 126 removes the edges of the structure that corresponds to the transmitting station, and extracts the edges of other structures. The processing for removing the edges of the structure that corresponds to the transmitting station may be performed by the generation unit 128.
- The generation unit 128 has a
judgment unit 130 and adetermination unit 132, and is configured to generate input data (input parameters) used for machine learning performed by thelearning unit 14, based on the information received from thecalculation unit 122 and the processing unit 126, and output the input data to thelearning unit 14. The information input to the generation unit 128 from thecalculation unit 122 and the processing unit 126 includes the position information for the transmitting station and the receiving station, the three-dimensional distance (slope distance d3D), the free space loss LFS, and edges (an edge image). - For example, using the position information for the transmitting station and the receiving station that was received from the
calculation unit 122 and the edges (the edge image) that were received from the processing unit 126, thejudgment unit 130 judges whether or not a line segment that connects the transmitting station and the receiving station intersects an edge, and outputs the judgment result to thedetermination unit 132. - Here, the
judgment unit 130 sets the result of the judgment regarding whether or not the line segment intersects an edge as a line-of-sight judgment FLOS. For example, if thejudgment unit 130 has judged that the line segment intersects an edge, the line-of-sight judgment FLOS is affirmative. Also, if thejudgment unit 130 has judged that the line segment does not intersect an edge, the line-of-sight judgment FLOS is negative. - If the
judgment unit 130 has judged that the line-of-sight judgment FLOS is affirmative, thedetermination unit 132 sets a first distance (dnTx) to the distance from the transmitting station to the nearest structure edge, and sets a second distance (dnRx) to the distance from the receiving station to the nearest structure edge. Also, if thejudgment unit 130 has judged that the line-of-sight judgment FLOS is negative, thedetermination unit 132 sets the first distance (dnTx) and the second distance (dnRx) to the two-dimensional distance (slope distance d2D) between the transmitting station and the receiving station. - Note that the two-dimensional distance (slope distance d2D(between the transmitting station and the receiving station is expressed by the following
Expression 3. -
[Math 3] -
d 2D=√{square root over ((x Tx −x Rx)2+(y Tx −y Rx)2)} (3) - The
determination unit 132 then makes a determination that the first distance (dnTx) and the second distance (dnRx) that were set are to be included in the input data that is to be used in the machine learning performed by thelearning unit 14. The input data used in the machine learning performed by thelearning unit 14 includes, for example, the three-dimensional distance (slope distance d3D), the frequency f, the free space loss LFS, the judgment result regarding the line-of-sight judgment FLOS, the first distance (dnTx), and the second distance (dnRx). - Using a neural network for example, the
learning unit 14 performs machine learning with use of the above-described input data received from the generation unit 128 and the propagation loss L as learning parameters, and stores the learned model in themodel storage unit 16. -
FIG. 4 is a diagram illustrating a multi-layer perceptron used by thelearning unit 14. In the input layer, the hidden layer, and the output layer, ω represents a weight matrix and b represents a constant term array. Using the three-dimensional distance (slope distance d3D), the frequency f, the free space loss LFS, the judgment result regarding the line-of-sight judgment FLOS, the first distance (dnTx), the second distance (dnRx), and the like as input parameters, thelearning unit 14 performs learning to adjust the weights of the layers. - The propagation
characteristic estimation device 1 then estimates the propagation characteristics of radio waves between the transmitting station and the receiving station with use of the model stored in themodel storage unit 16. - Next, an example of operations of the propagation
characteristic estimation device 1 will be described.FIG. 5 is a flowchart showing an example of operations in the case where the propagationcharacteristic estimation device 1 performs machine learning. - As shown in
FIG. 5 , in the propagationcharacteristic estimation device 1, thecalculation unit 122 calculates the slope distance d3D using the positions of the transmitting station and the receiving station (transmitting and receiving station positions) (S100). Also, thecalculation unit 122 calculates the free space loss LFS (S102). - The acquisition unit 124 imports a satellite photograph of the estimation range from the image storage unit 2 (S104), and then the processing unit 126 extracts the edges of structures such as buildings included in the satellite photograph (S106).
- Next, the
judgment unit 130 calculates the line-of-sight judgment FLOS between the transmitting and receiving stations (S108), and thedetermination unit 132 performs calculation to determine the distance information (the first distance (dnTx) and the second distance (dnRx)) between a building and the transmitting and receiving stations (S110). - The
learning unit 14 performs learning using the free space loss LFS, the judgment result regarding the line-of-sight judgment FLOS, the distance information on the distances to the building, and the like (S112). - Next, a specific example of operations of the input data generation unit 12 will be described.
FIG. 6 is a flowchart showing a specific example of operations of the input data generation unit 12. - As shown in
FIG. 6 , in the input data generation unit 12, thecalculation unit 122 calculates the slope distance d3D using the transmitting and receiving station positions (S200), and sets the slope distance in the propagationcharacteristic estimation device 1 to d3D (S202). - Then, the
calculation unit 122 calculates the free space loss LFS using above Expression 2 (S204). - The processing unit 126 creates an edge image from the two-dimensional image imported by the acquisition unit 124, and removes the transmitting station building from the created edge image (S206).
- Next, the
judgment unit 130 makes the judgment of whether or riot the line segment between the transmitting and receiving stations intersects an edge (S208), and sets the result of the intersection judgment as the line-of-sight judgment FLOS (S210). Then, if thejudgment unit 130 has judged that the line-of-sight judgment FLOS is affirmative (S212: Yes), the generation unit 128 moves to the processing of S214, whereas if thejudgment unit 130 has judged that the line-of-sight judgment FLOS is negative (S212: No), the generation unit 128 moves to the processing of S222. - The
determination unit 132 calculates the distance from the transmitting station to the nearest building (S214) and sets that distance as the first distance (dnTx) (S216). Also, thedetermination unit 132 calculates the distance from the receiving station to the nearest building (S218), and sets that distance as the second distance (dnRx) (S220). - In the processing of S222, the
determination unit 132 calculates the distance between the transmitting and receiving stations (slope distance d2D), and sets that distance as the first distance (dnTx) and the second distance (dnRx) (S224). - In this way, using a two-dimensional image of a region that includes a transmitting station and a receiving station, the propagation
characteristic estimation device 1 extracts edges of structures in a two-dimensional image and generates input data that is to be used for machine learning, thus making it possible to reduce the storage capacity and reading time required for data that is needed to estimate the propagation characteristics of radio waves. - Note that some or all of the functions of the propagation
characteristic estimation device 1 may be constituted by hardware, or may be constituted as a program executed by a processor such as a CPU. - In other words, the propagation
characteristic estimation device 1 according to the present invention can be realized using a computer and a program, and the program can be recorded on a storage medium or provided through a network. -
FIG. 7 is a diagram showing an example of the hardware configuration of the propagationcharacteristic estimation device 1 according to the embodiment. As shown inFIG. 7 , in the propagationcharacteristic estimation device 1, an input unit 40, an output unit 41, acommunication unit 42, a CPU 43, a memory 44, and anHDD 45 are connected via a bus 46, for example, and function as a computer. Also, the propagationcharacteristic estimation device 1 is capable of inputting data to thestorage medium 47 and receiving data therefrom. - The input unit 40 is a keyboard, a mouse, or the like, and corresponds to the above-mentioned input unit 10. The output unit 41 is a display device such as a display. The
communication unit 42 is a wired and wireless network interface, for example. - The CPU 43 controls the units that constitute the propagation
characteristic estimation device 1, and performs the above-described calculation and the like. The memory 44 and theHDD 45 constitute a storage unit for storing data. In particular, the memory 44 stores the data used in the above-described calculation. Thestorage medium 47 is capable of storing a propagation characteristic estimation program or the like that executes the functions of the propagationcharacteristic estimation device 1. Note that the architecture that constitutes the propagationcharacteristic estimation device 1 is not limited to the example shown in.FIG. 7 - The embodiments described above are given as examples of embodiments of the present invention, rather than limiting the present invention, and the present invention can also be implemented in various other variations and modified embodiments.
-
- 1 Propagation characteristic estimation device
- 2 Image storage unit
- 10 Input unit
- 12 Input data generation unit
- 14 Learning unit
- 16 Model storage unit
- 40 Input unit
- 41 Output unit
- 42 Communication unit
- 43 CPU
- 44 Memory
- 45 HDD
- 46 Bus
- 47 Storage medium
- 120 Extraction unit
- 122 Calculation unit
- 124 Acquisition unit
- 126 Processing unit
- 128 Generation unit
- 130 Judgment unit
- 132 Determination unit
Claims (5)
1. A propagation characteristic estimation device for estimating a propagation characteristic of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristic estimation device comprising:
a processor; and
a storage medium having computer program instructions stored thereon, when executed by the processor, perform to:
based on input information from an external source, extract position information regarding the transmitting station and the receiving station and a frequency of radio waves transmitted by the transmitting station;
calculate a three-dimensional distance between the transmitting station and the receiving station and a free space loss of radio waves based on the position information and the frequency;
perform processing for, with use of a two-dimensional image of a region that includes the transmitting station and the receiving station, extracting an edge of a structure that reflects radio waves in the two-dimensional image;
generate input data for use in machine learning, based on the position information, the three-dimensional distance, the free space loss, and the edge; and
perform machine learning to estimate a propagation characteristic of radio waves between the transmitting station and the receiving station with use of the input data generated by the generation unit.
2. The propagation characteristic estimation device according to claim 1 , wherein the computer program instructions further perform to
judge whether or not a line segment that connects the transmitting station and the receiving station intersects the edge, and
in a case where the judgment unit judged that the line segment and the edge intersect, set a first distance to a distance from the transmitting station to a nearest structure edge and set a second distance to a distance from the receiving station to a nearest structure edge, in a case where the judgment unit judged that the line segment and the edge do not intersect, set the first distance and the second distance to a two-dimensional distance between the transmitting station and the receiving station, and make a determination that the first distance and the second distance that were set are to be included in the input data.
3. A propagation characteristic estimation method for estimating a propagation characteristic of radio waves between a transmitting station and a receiving station that perform wireless communication, the propagation characteristic estimation method comprising:
an extraction step of, based on input information from an external source, extracting position information regarding the transmitting station and the receiving station and a frequency of radio waves transmitted by the transmitting station;
a calculation step of calculating a three-dimensional distance between the transmitting station and the receiving station and a free space loss of radio waves based on the position information and the frequency;
a processing step of performing processing for, with use of a two-dimensional image of a region that includes the transmitting station and the receiving station, extracting an edge of a structure that reflects radio waves in the two-dimensional image;
a generation step of generating input data for use in machine learning, based on the position information, the three-dimensional distance, the free space loss, and the edge; and
a learning step of performing machine learning to estimate a propagation characteristic of radio waves between the transmitting station and the receiving station with use of the input data that was generated.
4. The propagation characteristic estimation method according to claim 3 ,
wherein the generation step includes
a judgment step of judging whether or not a line segment that connects the transmitting station and the receiving station intersects the edge, and
a determination step of, in a case where it was judged that the line segment and the edge intersect, setting a first distance to a distance from the transmitting station to a nearest structure edge and setting a second distance to a distance from the receiving station to a nearest structure edge, in a case where it was judged that the line segment and the edge do not intersect, setting the first distance and the second distance to a two-dimensional distance between the transmitting station and the receiving station, and making a determination that the first distance and the second distance that were set are to be included in the input data.
5. A propagation characteristic estimation program for causing a computer to function as the propagation characteristic estimation device according to claim 1 .
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2019/039353 WO2021064999A1 (en) | 2019-10-04 | 2019-10-04 | Propagation characteristic inference device, propagation characteristic inference method, and propagation characteristic inference program |
Publications (1)
Publication Number | Publication Date |
---|---|
US20220345899A1 true US20220345899A1 (en) | 2022-10-27 |
Family
ID=75336866
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/765,114 Pending US20220345899A1 (en) | 2019-10-04 | 2019-10-04 | Propagation characteristic estimation device, propagation characteristic estimation method, and propagation characteristic estimation program |
Country Status (3)
Country | Link |
---|---|
US (1) | US20220345899A1 (en) |
JP (1) | JP7400826B2 (en) |
WO (1) | WO2021064999A1 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7166503B2 (en) * | 2020-08-21 | 2022-11-07 | 三菱電機株式会社 | Radio wave propagation estimation device and map information extraction method |
CN113329437B (en) * | 2021-06-07 | 2022-07-01 | 北京邮电大学 | Wireless network signal propagation path loss prediction method and electronic equipment |
JP2023064837A (en) * | 2021-10-27 | 2023-05-12 | セイコーグループ株式会社 | Communication device, communication system, and communication method |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040259554A1 (en) * | 2003-04-23 | 2004-12-23 | Rappaport Theodore S. | System and method for ray tracing using reception surfaces |
US20070010207A1 (en) * | 2005-07-05 | 2007-01-11 | Dooley John A | System and method for the ultra-precise analysis and characterization of RF propagation dynamics in wireless communication networks |
US7260408B2 (en) * | 2004-02-20 | 2007-08-21 | Airespace, Inc. | Wireless node location mechanism using antenna pattern diversity to enhance accuracy of location estimates |
US7379710B2 (en) * | 2003-03-26 | 2008-05-27 | Nec Corporation | Radio-wave propagation characteristic forecasting system and its method, and program |
US20090203373A1 (en) * | 2008-02-07 | 2009-08-13 | Eduardo Jesus Alvarez Medina | Modifying Mobile Network Signal Propagation Predictions |
US7634265B2 (en) * | 2004-03-17 | 2009-12-15 | Nec Corporation | Radio wave propagation characteristic estimation system, and its method and program |
US8340684B2 (en) * | 2009-07-08 | 2012-12-25 | Kyocera Corporation | Mobile station |
US8355680B2 (en) * | 2007-12-10 | 2013-01-15 | Nec Corporation | Radio wave propagation analysis result display system |
US8436768B2 (en) * | 2008-12-30 | 2013-05-07 | Trueposition, Inc. | Diversity time and frequency location receiver |
US8442552B2 (en) * | 2010-04-23 | 2013-05-14 | Hewlett-Packard Development Company, L.P. | Method and system for radio frequency coverage prediction in a multi-level wireless network |
US8630676B2 (en) * | 2010-07-22 | 2014-01-14 | Electronics And Telecommunications Research Institute | Wireless communication apparatus and method for transmitting a signal according to determined transmission power and transmission time |
US9121923B2 (en) * | 2008-12-30 | 2015-09-01 | Trueposition, Inc. | Interference detection, characterization and location in a wireless communications or broadcast system |
US9438499B2 (en) * | 2012-09-06 | 2016-09-06 | Intel Corporation | Approximation of the physical location of devices and transitive device discovery through the sharing of neighborhood information using wireless or wired discovery mechanisms |
US20180278349A1 (en) * | 2014-10-27 | 2018-09-27 | Ranplan Wireless Network Design Limited | Method for predicting outdoor three-dimensional space signal field strength by extended cost-231-walfisch-ikegami propagation model |
US10887029B2 (en) * | 2016-11-17 | 2021-01-05 | Samsung Electronics Co., Ltd. | Method and apparatus for analysing communication channel in consideration of material and contours of objects |
US11076328B2 (en) * | 2017-09-21 | 2021-07-27 | Sony Corporation | Apparatus and method in wireless communication system and computer readable storage medium |
US11395152B2 (en) * | 2017-12-18 | 2022-07-19 | Samsung Electronics Co., Ltd. | Method and apparatus for communication environment analysis and network design considering radio wave incoming unit of structure |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013026884A (en) * | 2011-07-22 | 2013-02-04 | Nippon Telegr & Teleph Corp <Ntt> | Propagation loss estimation method and program and propagation loss estimation device |
JP6781432B2 (en) * | 2017-08-01 | 2020-11-04 | 日本電信電話株式会社 | Radio wave propagation simulation model creation method, creation system, creation device and creation program |
JP7073112B2 (en) * | 2018-01-11 | 2022-05-23 | 株式会社Nttドコモ | Radio wave propagation estimation device, radio wave propagation estimation method, and radio wave propagation estimation program |
-
2019
- 2019-10-04 WO PCT/JP2019/039353 patent/WO2021064999A1/en active Application Filing
- 2019-10-04 JP JP2021550926A patent/JP7400826B2/en active Active
- 2019-10-04 US US17/765,114 patent/US20220345899A1/en active Pending
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7379710B2 (en) * | 2003-03-26 | 2008-05-27 | Nec Corporation | Radio-wave propagation characteristic forecasting system and its method, and program |
US20040259554A1 (en) * | 2003-04-23 | 2004-12-23 | Rappaport Theodore S. | System and method for ray tracing using reception surfaces |
US7260408B2 (en) * | 2004-02-20 | 2007-08-21 | Airespace, Inc. | Wireless node location mechanism using antenna pattern diversity to enhance accuracy of location estimates |
US7634265B2 (en) * | 2004-03-17 | 2009-12-15 | Nec Corporation | Radio wave propagation characteristic estimation system, and its method and program |
US20070010207A1 (en) * | 2005-07-05 | 2007-01-11 | Dooley John A | System and method for the ultra-precise analysis and characterization of RF propagation dynamics in wireless communication networks |
US8355680B2 (en) * | 2007-12-10 | 2013-01-15 | Nec Corporation | Radio wave propagation analysis result display system |
US20090203373A1 (en) * | 2008-02-07 | 2009-08-13 | Eduardo Jesus Alvarez Medina | Modifying Mobile Network Signal Propagation Predictions |
US8385908B2 (en) * | 2008-02-07 | 2013-02-26 | Optimi Corporation | Modifying mobile network signal propagation predictions |
US9121923B2 (en) * | 2008-12-30 | 2015-09-01 | Trueposition, Inc. | Interference detection, characterization and location in a wireless communications or broadcast system |
US8436768B2 (en) * | 2008-12-30 | 2013-05-07 | Trueposition, Inc. | Diversity time and frequency location receiver |
US8340684B2 (en) * | 2009-07-08 | 2012-12-25 | Kyocera Corporation | Mobile station |
US8442552B2 (en) * | 2010-04-23 | 2013-05-14 | Hewlett-Packard Development Company, L.P. | Method and system for radio frequency coverage prediction in a multi-level wireless network |
US8630676B2 (en) * | 2010-07-22 | 2014-01-14 | Electronics And Telecommunications Research Institute | Wireless communication apparatus and method for transmitting a signal according to determined transmission power and transmission time |
US9438499B2 (en) * | 2012-09-06 | 2016-09-06 | Intel Corporation | Approximation of the physical location of devices and transitive device discovery through the sharing of neighborhood information using wireless or wired discovery mechanisms |
US20180278349A1 (en) * | 2014-10-27 | 2018-09-27 | Ranplan Wireless Network Design Limited | Method for predicting outdoor three-dimensional space signal field strength by extended cost-231-walfisch-ikegami propagation model |
US10333638B2 (en) * | 2014-10-27 | 2019-06-25 | Ranplan Wireless Network Design Limited | Method for predicting outdoor three-dimensional space signal field strength by extended COST-231-Walfisch-Ikegami propagation model |
US10887029B2 (en) * | 2016-11-17 | 2021-01-05 | Samsung Electronics Co., Ltd. | Method and apparatus for analysing communication channel in consideration of material and contours of objects |
US11076328B2 (en) * | 2017-09-21 | 2021-07-27 | Sony Corporation | Apparatus and method in wireless communication system and computer readable storage medium |
US11653276B2 (en) * | 2017-09-21 | 2023-05-16 | Sony Group Corporation | Apparatus and method in wireless communication system and computer readable storage medium |
US11395152B2 (en) * | 2017-12-18 | 2022-07-19 | Samsung Electronics Co., Ltd. | Method and apparatus for communication environment analysis and network design considering radio wave incoming unit of structure |
Also Published As
Publication number | Publication date |
---|---|
WO2021064999A1 (en) | 2021-04-08 |
JP7400826B2 (en) | 2023-12-19 |
JPWO2021064999A1 (en) | 2021-04-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110731096B (en) | Predicting received signal strength in a telecommunications network using a deep neural network | |
Levie et al. | RadioUNet: Fast radio map estimation with convolutional neural networks | |
US20220345899A1 (en) | Propagation characteristic estimation device, propagation characteristic estimation method, and propagation characteristic estimation program | |
CN103701534B (en) | Wireless channel large scale fading factor computational methods and system | |
WO2015126499A2 (en) | Systems and methods for gnss snr probabilistic localization and 3-d mapping | |
EP2849117A1 (en) | Methods, apparatuses and computer program products for automatic, non-parametric, non-iterative three dimensional geographic modeling | |
CN114297730A (en) | Countermeasure image generation method, device and storage medium | |
JP4530898B2 (en) | Radio wave propagation estimation program, radio wave propagation estimation method, and apparatus for executing the method | |
JP6696859B2 (en) | Quality estimation device and quality estimation method | |
WO2022093329A1 (en) | Scheduling satellite data transmissions using differing sets of ground stations | |
JPWO2019107388A1 (en) | Position estimation system, position estimation method and program | |
Navarro et al. | Applicability of game engine for ray Tracing Techniques in a Complex Urban Environment | |
US20220210762A1 (en) | Device type state estimation | |
CN113111524B (en) | Antenna isolation degree prediction method based on far field test, storage medium and device | |
CN113644996A (en) | Cell-level RSRP estimation method based on deep learning | |
KR101504357B1 (en) | Method to extract and represent terrain obstacles for radio network optimization from measured drive-test data | |
Navarro et al. | Using game engines for wideband channel estimation parameters in Andean cities | |
CN115866656A (en) | Path loss calculation method and device | |
US20240137138A1 (en) | Communication design support apparatus, communication design support method and program | |
CN106612510B (en) | Method and apparatus for indoor coverage design | |
US11471772B2 (en) | System and method for deploying virtual replicas of real-world elements into a persistent virtual world system | |
EP3923236A1 (en) | Image-processing device, image-processing method, and image-processing computer program | |
JP6582976B2 (en) | Estimation apparatus, estimation method, and estimation program | |
US20240161386A1 (en) | Generative adversarial network based identification of induced deformation in three-dimensional object | |
KR101105064B1 (en) | Method to Optimize Antenna Configuration for NLOS Area using Dominant Path |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: NIPPON TELEGRAPH AND TELEPHONE CORPORATION, JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:KUNO, NOBUAKI;YAMADA, WATARU;MORIYAMA, TAKATSUNE;AND OTHERS;SIGNING DATES FROM 20210114 TO 20220420;REEL/FRAME:059871/0741 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |